摘要
以下引文由新闻编辑从发明人提供的背景信息中获得：“监督分类任务模型使用由话语(自然语言如英语中的文本串)和将话语分类为几个类别之一的标签(文献中通常称为意图)组成的例子进行训练。分类可以简单地分为“积极的”、“消极的”和“中性的”，一种方法是根据其中的情感对个别话语进行分类。“Yay that’s great”可以归类为“积极的”，而“Terrible,just Terrible”可以归类为“消极的”。这是一个简单的例子，一般来说，分类本体可能是任意复杂的，有几十个、几百个或更多的
Abstract
The following quote was obtained by the news editors from the background informa tion supplied by the inventors: “Supervised classification task models are train ed using examples consisting of utterances (strings of text in a natural languag e such as English), and a label which classifies the utterance into one of sever al classes (commonly called intents in the literature). For example, the classif ication may be as simple as “Positive”, “Negative”, and “Neutral”, and one wishe s to classify individual utterances based on the sentiment therein. “Yay that’s great” may be classified as “Positive” while “Terrible, just terrible” may be cl assified as “Negative”. This is one simple example, and in general the classific ation ontology may be arbitrarily complex, with tens, hundreds, or more possible classes.
NETL
NSTL